The Experts below are selected from a list of 327 Experts worldwide ranked by ideXlab platform

Robert J Harmon - One of the best experts on this subject based on the ideXlab platform.

  • selection and use of Inferential Statistics a summary
    Journal of the American Academy of Child and Adolescent Psychiatry, 2003
    Co-Authors: George A Morgan, Jeffrey A Gliner, Robert J Harmon
    Abstract:

    The interpretation of many of the Inferential Statistics found in recent issues of this journal has been discussed in our last eight columns. In the present column, we summarize and extend these recent columns to some additional Statistics. Several figures are presented to help in the selection of an appropriate statistical test. It is also possible to work backward: start with the statistic mentioned in an article that you are reading and then refer to the figures to get a better idea of why the authors chose that statistic. Remember that, for heuristic reasons, we have divided research questions into difference questions and associational questions. Difference questions compare groups and utilize the Statistics, which we call difference Inferential Statistics (see the left side of Fig. 1). These Statistics (e.g., t test and analysis of variance) (ANOVA) are identified in Figures 2 and 4. Associational questions examine the association or relationship between two or more variables (see the right side of Fig. 1). They utilize associational Inferential Statistics (correlation and regression) and are shown in Figures 3 and 5. It is worth noting that there may be more than one appropriate statistical analysis for a given design or configuration of variables; thus Figures 2–5 just provide guidelines. As we shall see in the section below on the general linear model (GLM), many difference Statistics have an analog associational statistic.

  • selection of Inferential Statistics an overview
    Journal of the American Academy of Child and Adolescent Psychiatry, 2002
    Co-Authors: George A Morgan, Jeffrey A Gliner, Robert J Harmon
    Abstract:

    : This column serves as an introduction to selection of appropriate statistical methods. In the next five columns we will discuss conceptually, and in more depth, these statistical methods. We will use clinical examples and discuss why the author(s) selected a particular statistical method and how the results of the statistical method were interpreted.

  • introduction to Inferential Statistics and hypothesis testing
    Journal of the American Academy of Child and Adolescent Psychiatry, 2000
    Co-Authors: Jeffrey A Gliner, George A Morgan, Robert J Harmon
    Abstract:

    When performing research, rarely are we able to work with an entire population of individuals. Instead, we usually test our treatment or intervention on a sample of individuals from the population. It is hoped that, if our treatment is successful, we can infer that the results from our sample apply to the population of interest. Inferential Statistics involves making inferences from sample Statistics, such as the sample mean and the sample standard deviation, to population parameters such as the population mean and the population standard deviation. Suppose we are interested in the relationship between exercise and quality of life in depressed adolescent patients. A reasonable hypothesis is that depressed patients who exercise regularly will have higher quality-of-life scores than those who do not exercise regularly. Inferential Statistics provides us with a way to test this hypothesis, i.e., make a decision about the relationship between exercise and quality of life in depressed adolescent patients. To test our hypothesis, we need to reformulate it as two statements or hypotheses, the null hypothesis and the alternative hypothesis. However, before we actually specify the null and alternative hypotheses for our study, we need to operationalize our variables. The independent variable, exercise, will be defined as either use of a stationary bicycle 45 minutes per day (5 days per week for 6 weeks at a work load of 50% of maximum capacity) or no prescribed exercise. The dependent variable, a quality-of-life inventory (QL), is an indicator of quality of life and is measured as a score between 1 and 100. If our hypothesis is correct, we would expect that subjects who exercise will have a higher quality-of-life index than those who do not exercise regularly, and a higher score on the inventory would indicate improvement in these depressed adolescents. (This assumes an increased score from baseline in the intervention group. A difference could also occur if there is worsening in the nonexercising adolescents.) The null hypothesis states that the mean QL of the population of those who receive the intervention is equal to the mean QL of the population of those who do not receive the intervention. If the null hypothesis is true, the intervention of exercise has not been successful in changing quality of life. The alternative hypothesis states that the mean QL of the population of those who receive the intervention will be greater than the mean QL of the population of those who do not receive the intervention. If the null hypothesis is false, or rejected, the

George A Morgan - One of the best experts on this subject based on the ideXlab platform.

  • selection and use of Inferential Statistics a summary
    Journal of the American Academy of Child and Adolescent Psychiatry, 2003
    Co-Authors: George A Morgan, Jeffrey A Gliner, Robert J Harmon
    Abstract:

    The interpretation of many of the Inferential Statistics found in recent issues of this journal has been discussed in our last eight columns. In the present column, we summarize and extend these recent columns to some additional Statistics. Several figures are presented to help in the selection of an appropriate statistical test. It is also possible to work backward: start with the statistic mentioned in an article that you are reading and then refer to the figures to get a better idea of why the authors chose that statistic. Remember that, for heuristic reasons, we have divided research questions into difference questions and associational questions. Difference questions compare groups and utilize the Statistics, which we call difference Inferential Statistics (see the left side of Fig. 1). These Statistics (e.g., t test and analysis of variance) (ANOVA) are identified in Figures 2 and 4. Associational questions examine the association or relationship between two or more variables (see the right side of Fig. 1). They utilize associational Inferential Statistics (correlation and regression) and are shown in Figures 3 and 5. It is worth noting that there may be more than one appropriate statistical analysis for a given design or configuration of variables; thus Figures 2–5 just provide guidelines. As we shall see in the section below on the general linear model (GLM), many difference Statistics have an analog associational statistic.

  • selection of Inferential Statistics an overview
    Journal of the American Academy of Child and Adolescent Psychiatry, 2002
    Co-Authors: George A Morgan, Jeffrey A Gliner, Robert J Harmon
    Abstract:

    : This column serves as an introduction to selection of appropriate statistical methods. In the next five columns we will discuss conceptually, and in more depth, these statistical methods. We will use clinical examples and discuss why the author(s) selected a particular statistical method and how the results of the statistical method were interpreted.

  • introduction to Inferential Statistics and hypothesis testing
    Journal of the American Academy of Child and Adolescent Psychiatry, 2000
    Co-Authors: Jeffrey A Gliner, George A Morgan, Robert J Harmon
    Abstract:

    When performing research, rarely are we able to work with an entire population of individuals. Instead, we usually test our treatment or intervention on a sample of individuals from the population. It is hoped that, if our treatment is successful, we can infer that the results from our sample apply to the population of interest. Inferential Statistics involves making inferences from sample Statistics, such as the sample mean and the sample standard deviation, to population parameters such as the population mean and the population standard deviation. Suppose we are interested in the relationship between exercise and quality of life in depressed adolescent patients. A reasonable hypothesis is that depressed patients who exercise regularly will have higher quality-of-life scores than those who do not exercise regularly. Inferential Statistics provides us with a way to test this hypothesis, i.e., make a decision about the relationship between exercise and quality of life in depressed adolescent patients. To test our hypothesis, we need to reformulate it as two statements or hypotheses, the null hypothesis and the alternative hypothesis. However, before we actually specify the null and alternative hypotheses for our study, we need to operationalize our variables. The independent variable, exercise, will be defined as either use of a stationary bicycle 45 minutes per day (5 days per week for 6 weeks at a work load of 50% of maximum capacity) or no prescribed exercise. The dependent variable, a quality-of-life inventory (QL), is an indicator of quality of life and is measured as a score between 1 and 100. If our hypothesis is correct, we would expect that subjects who exercise will have a higher quality-of-life index than those who do not exercise regularly, and a higher score on the inventory would indicate improvement in these depressed adolescents. (This assumes an increased score from baseline in the intervention group. A difference could also occur if there is worsening in the nonexercising adolescents.) The null hypothesis states that the mean QL of the population of those who receive the intervention is equal to the mean QL of the population of those who do not receive the intervention. If the null hypothesis is true, the intervention of exercise has not been successful in changing quality of life. The alternative hypothesis states that the mean QL of the population of those who receive the intervention will be greater than the mean QL of the population of those who do not receive the intervention. If the null hypothesis is false, or rejected, the

Zulkifli Yusop - One of the best experts on this subject based on the ideXlab platform.

  • soft computing Inferential Statistics of 3d rainfall runoff modelling in peninsula malaysia
    Malaysian Technical Universities Conference on Engineering and Technology 2015, 2015
    Co-Authors: Lloyd Ling, Zulkifli Yusop
    Abstract:

    Thorough understanding of the rainfall-runoff processes that influence watershed hydrological response is important and can be incorporated into the planning and management of watershed resources. Soft computing techniques and Inferential Statistics were used to assess 2 rainfall-runoff models and their runoff predictive accuracy. The 1954 simplified SCS runoff model was statistical in-significant under two Null hypotheses rejection and paved way for the model calibration study to produce regional specific model through calibration according to regional hydrological conditions. New model out-performed non-calibrated SCS model and reduced RSS by 27%. A 3D runoff difference model was created as a collective visual representation between non-calibrated and calibrated new model, it also showed that both under and over design risks were less significant at high CN area and more profound under high rainfall depths. On average, rural catchments of Peninsula Malaysia faced 7% (lower CN area as much as 22%) CN down scaling adjustment due to regional hydrological calibration in order to achieve better runoff predictions.

  • Inferential Statistics assessment of urban rainfall runoff models
    Malaysian Technical Universities Conference on Engineering and Technology 2015, 2015
    Co-Authors: Lloyd Ling, Zulkifli Yusop
    Abstract:

    Thorough understanding of the rainfall-runoff processes that influence watershed hydrological response is important and can be incorporated into the planning and management of water resources. This study assessed rainfall-runoff models through Inferential Statistics and benchmarked their runoff predictive accuracies against a proposed new runoff model. Linear regression model has been in use to model urban rainfall-runoff. However, the model was found to be statistically in-significant in this study. Hydrological implications from the regression model became in-consistent and obsolete. The 1954 simplified SCS runoff model was also statistical in-significant under two Null hypotheses rejection and paved way for the regional model calibration study. A new rainfall-runoff model was developed with calibration according to regional hydrological conditions. It out-performed simplified SCS runoff model and reduced RSS by 54%.

  • Inferential Statistics of claim assessment
    INTERNATIONAL CONFERENCE ON QUANTITATIVE SCIENCES AND ITS APPLICATIONS (ICOQSIA 2014): Proceedings of the 3rd International Conference on Quantitative, 2014
    Co-Authors: Lloyd Ling, Zulkifli Yusop
    Abstract:

    Initial abstraction coefficient ratio (λ) within the runoff prediction model proposed by the United States Department of Agriculture (USDA), Soil Conservation Services (SCS) in 1954 produced inconsistent runoff results according to worldwide research findings. SCS proposed a linear correlation between initial abstraction (Ia) and total abstraction (S) where Ia = λS. The proposed correlation by then was re-assessed using non-parametric Inferential Statistics to deduce a different conclusion in this study. Practitioners are encouraged to validate and employ the runoff prediction model with caution.

Jeffrey A Gliner - One of the best experts on this subject based on the ideXlab platform.

  • selection and use of Inferential Statistics a summary
    Journal of the American Academy of Child and Adolescent Psychiatry, 2003
    Co-Authors: George A Morgan, Jeffrey A Gliner, Robert J Harmon
    Abstract:

    The interpretation of many of the Inferential Statistics found in recent issues of this journal has been discussed in our last eight columns. In the present column, we summarize and extend these recent columns to some additional Statistics. Several figures are presented to help in the selection of an appropriate statistical test. It is also possible to work backward: start with the statistic mentioned in an article that you are reading and then refer to the figures to get a better idea of why the authors chose that statistic. Remember that, for heuristic reasons, we have divided research questions into difference questions and associational questions. Difference questions compare groups and utilize the Statistics, which we call difference Inferential Statistics (see the left side of Fig. 1). These Statistics (e.g., t test and analysis of variance) (ANOVA) are identified in Figures 2 and 4. Associational questions examine the association or relationship between two or more variables (see the right side of Fig. 1). They utilize associational Inferential Statistics (correlation and regression) and are shown in Figures 3 and 5. It is worth noting that there may be more than one appropriate statistical analysis for a given design or configuration of variables; thus Figures 2–5 just provide guidelines. As we shall see in the section below on the general linear model (GLM), many difference Statistics have an analog associational statistic.

  • selection of Inferential Statistics an overview
    Journal of the American Academy of Child and Adolescent Psychiatry, 2002
    Co-Authors: George A Morgan, Jeffrey A Gliner, Robert J Harmon
    Abstract:

    : This column serves as an introduction to selection of appropriate statistical methods. In the next five columns we will discuss conceptually, and in more depth, these statistical methods. We will use clinical examples and discuss why the author(s) selected a particular statistical method and how the results of the statistical method were interpreted.

  • introduction to Inferential Statistics and hypothesis testing
    Journal of the American Academy of Child and Adolescent Psychiatry, 2000
    Co-Authors: Jeffrey A Gliner, George A Morgan, Robert J Harmon
    Abstract:

    When performing research, rarely are we able to work with an entire population of individuals. Instead, we usually test our treatment or intervention on a sample of individuals from the population. It is hoped that, if our treatment is successful, we can infer that the results from our sample apply to the population of interest. Inferential Statistics involves making inferences from sample Statistics, such as the sample mean and the sample standard deviation, to population parameters such as the population mean and the population standard deviation. Suppose we are interested in the relationship between exercise and quality of life in depressed adolescent patients. A reasonable hypothesis is that depressed patients who exercise regularly will have higher quality-of-life scores than those who do not exercise regularly. Inferential Statistics provides us with a way to test this hypothesis, i.e., make a decision about the relationship between exercise and quality of life in depressed adolescent patients. To test our hypothesis, we need to reformulate it as two statements or hypotheses, the null hypothesis and the alternative hypothesis. However, before we actually specify the null and alternative hypotheses for our study, we need to operationalize our variables. The independent variable, exercise, will be defined as either use of a stationary bicycle 45 minutes per day (5 days per week for 6 weeks at a work load of 50% of maximum capacity) or no prescribed exercise. The dependent variable, a quality-of-life inventory (QL), is an indicator of quality of life and is measured as a score between 1 and 100. If our hypothesis is correct, we would expect that subjects who exercise will have a higher quality-of-life index than those who do not exercise regularly, and a higher score on the inventory would indicate improvement in these depressed adolescents. (This assumes an increased score from baseline in the intervention group. A difference could also occur if there is worsening in the nonexercising adolescents.) The null hypothesis states that the mean QL of the population of those who receive the intervention is equal to the mean QL of the population of those who do not receive the intervention. If the null hypothesis is true, the intervention of exercise has not been successful in changing quality of life. The alternative hypothesis states that the mean QL of the population of those who receive the intervention will be greater than the mean QL of the population of those who do not receive the intervention. If the null hypothesis is false, or rejected, the

Lloyd Ling - One of the best experts on this subject based on the ideXlab platform.

  • soft computing Inferential Statistics of 3d rainfall runoff modelling in peninsula malaysia
    Malaysian Technical Universities Conference on Engineering and Technology 2015, 2015
    Co-Authors: Lloyd Ling, Zulkifli Yusop
    Abstract:

    Thorough understanding of the rainfall-runoff processes that influence watershed hydrological response is important and can be incorporated into the planning and management of watershed resources. Soft computing techniques and Inferential Statistics were used to assess 2 rainfall-runoff models and their runoff predictive accuracy. The 1954 simplified SCS runoff model was statistical in-significant under two Null hypotheses rejection and paved way for the model calibration study to produce regional specific model through calibration according to regional hydrological conditions. New model out-performed non-calibrated SCS model and reduced RSS by 27%. A 3D runoff difference model was created as a collective visual representation between non-calibrated and calibrated new model, it also showed that both under and over design risks were less significant at high CN area and more profound under high rainfall depths. On average, rural catchments of Peninsula Malaysia faced 7% (lower CN area as much as 22%) CN down scaling adjustment due to regional hydrological calibration in order to achieve better runoff predictions.

  • Inferential Statistics assessment of urban rainfall runoff models
    Malaysian Technical Universities Conference on Engineering and Technology 2015, 2015
    Co-Authors: Lloyd Ling, Zulkifli Yusop
    Abstract:

    Thorough understanding of the rainfall-runoff processes that influence watershed hydrological response is important and can be incorporated into the planning and management of water resources. This study assessed rainfall-runoff models through Inferential Statistics and benchmarked their runoff predictive accuracies against a proposed new runoff model. Linear regression model has been in use to model urban rainfall-runoff. However, the model was found to be statistically in-significant in this study. Hydrological implications from the regression model became in-consistent and obsolete. The 1954 simplified SCS runoff model was also statistical in-significant under two Null hypotheses rejection and paved way for the regional model calibration study. A new rainfall-runoff model was developed with calibration according to regional hydrological conditions. It out-performed simplified SCS runoff model and reduced RSS by 54%.

  • Inferential Statistics of claim assessment
    INTERNATIONAL CONFERENCE ON QUANTITATIVE SCIENCES AND ITS APPLICATIONS (ICOQSIA 2014): Proceedings of the 3rd International Conference on Quantitative, 2014
    Co-Authors: Lloyd Ling, Zulkifli Yusop
    Abstract:

    Initial abstraction coefficient ratio (λ) within the runoff prediction model proposed by the United States Department of Agriculture (USDA), Soil Conservation Services (SCS) in 1954 produced inconsistent runoff results according to worldwide research findings. SCS proposed a linear correlation between initial abstraction (Ia) and total abstraction (S) where Ia = λS. The proposed correlation by then was re-assessed using non-parametric Inferential Statistics to deduce a different conclusion in this study. Practitioners are encouraged to validate and employ the runoff prediction model with caution.